In [1]:
pip install tensorflow

Collecting tensorflow
  Downloading tensorflow-2.8.0-cp38-cp38-win_amd64.whl (438.0 MB)
Collecting grpcio<2.0,>=1.24.3
  Downloading grpcio-1.44.0-cp38-cp38-win_amd64.whl (3.4 MB)
Collecting tf-estimator-nightly==2.8.0.dev2021122109
  Downloading tf_estimator_nightly-2.8.0.dev2021122109-py2.py3-none-any.whl (462 kB)
Collecting wrapt>=1.11.0
  Downloading wrapt-1.14.0-cp38-cp38-win_amd64.whl (36 kB)
Collecting google-pasta>=0.1.1
  Downloading google_pasta-0.2.0-py3-none-any.whl (57 kB)
Collecting absl-py>=0.4.0
  Downloading absl_py-1.0.0-py3-none-any.whl (126 kB)
Collecting protobuf>=3.9.2
  Downloading protobuf-3.20.0-cp38-cp38-win_amd64.whl (904 kB)
Requirement already satisfied: setuptools in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from tensorflow) (58.0.4)
Collecting keras-preprocessing>=1.1.1
  Downloading Keras_Preprocessing-1.1.2-py2.py3-none-any.whl (42 kB)
Collecting tensorflow-io-gcs-filesystem>=0.23.1
  Downloading tensorflow_io_gcs_filesystem-0.24.0-cp38-cp38-win_amd64.whl (1.5 MB)
Collecting tensorboard<2.9,>=2.8
  Downloading tensorboard-2.8.0-py3-none-any.whl (5.8 MB)
Collecting libclang>=9.0.1
  Downloading libclang-13.0.0-py2.py3-none-win_amd64.whl (13.9 MB)
Collecting termcolor>=1.1.0
  Downloading termcolor-1.1.0.tar.gz (3.9 kB)
Collecting flatbuffers>=1.12
  Downloading flatbuffers-2.0-py2.py3-none-any.whl (26 kB)
Collecting h5py>=2.9.0
  Downloading h5py-3.6.0-cp38-cp38-win_amd64.whl (2.8 MB)
Collecting astunparse>=1.6.0
  Downloading astunparse-1.6.3-py2.py3-none-any.whl (12 kB)
Collecting gast>=0.2.1
  Downloading gast-0.5.3-py3-none-any.whl (19 kB)
Requirement already satisfied: six>=1.12.0 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from tensorflow) (1.16.0)
Collecting opt-einsum>=2.3.2
  Downloading opt_einsum-3.3.0-py3-none-any.whl (65 kB)
Requirement already satisfied: typing-extensions>=3.6.6 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from tensorflow) (4.1.1)
Collecting numpy>=1.20
  Downloading numpy-1.22.3-cp38-cp38-win_amd64.whl (14.7 MB)
Collecting keras<2.9,>=2.8.0rc0
  Downloading keras-2.8.0-py2.py3-none-any.whl (1.4 MB)
Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from astunparse>=1.6.0->tensorflow) (0.37.1)
Collecting requests<3,>=2.21.0
  Downloading requests-2.27.1-py2.py3-none-any.whl (63 kB)
Collecting tensorboard-plugin-wit>=1.6.0
  Downloading tensorboard_plugin_wit-1.8.1-py3-none-any.whl (781 kB)
Collecting tensorboard-data-server<0.7.0,>=0.6.0
  Downloading tensorboard_data_server-0.6.1-py3-none-any.whl (2.4 kB)
Collecting markdown>=2.6.8
  Downloading Markdown-3.3.6-py3-none-any.whl (97 kB)
Collecting google-auth-oauthlib<0.5,>=0.4.1
  Downloading google_auth_oauthlib-0.4.6-py2.py3-none-any.whl (18 kB)
Collecting werkzeug>=0.11.15
  Downloading Werkzeug-2.1.1-py3-none-any.whl (224 kB)
Collecting google-auth<3,>=1.6.3
  Downloading google_auth-2.6.2-py2.py3-none-any.whl (156 kB)
Collecting rsa<5,>=3.1.4
  Downloading rsa-4.8-py3-none-any.whl (39 kB)
Collecting cachetools<6.0,>=2.0.0
  Downloading cachetools-5.0.0-py3-none-any.whl (9.1 kB)
Collecting pyasn1-modules>=0.2.1
  Downloading pyasn1_modules-0.2.8-py2.py3-none-any.whl (155 kB)
Collecting requests-oauthlib>=0.7.0
  Downloading requests_oauthlib-1.3.1-py2.py3-none-any.whl (23 kB)
Requirement already satisfied: importlib-metadata>=4.4 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from markdown>=2.6.8->tensorboard<2.9,>=2.8->tensorflow) (4.11.3)
Requirement already satisfied: zipp>=0.5 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard<2.9,>=2.8->tensorflow) (3.7.0)
Collecting pyasn1<0.5.0,>=0.4.6
  Downloading pyasn1-0.4.8-py2.py3-none-any.whl (77 kB)
Collecting urllib3<1.27,>=1.21.1
  Downloading urllib3-1.26.9-py2.py3-none-any.whl (138 kB)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow) (2021.10.8)
Collecting idna<4,>=2.5
  Downloading idna-3.3-py3-none-any.whl (61 kB)
Collecting charset-normalizer~=2.0.0
  Downloading charset_normalizer-2.0.12-py3-none-any.whl (39 kB)
Collecting oauthlib>=3.0.0
  Downloading oauthlib-3.2.0-py3-none-any.whl (151 kB)
Building wheels for collected packages: termcolor
  Building wheel for termcolor (setup.py): started
  Building wheel for termcolor (setup.py): finished with status 'done'
  Created wheel for termcolor: filename=termcolor-1.1.0-py3-none-any.whl size=4848 sha256=485dc65a087ecfada9bfb4ddc3dd182f907d01193685af9436dca22a7c5f9b41
  Stored in directory: c:\users\krudko\appdata\local\pip\cache\wheels\a0\16\9c\5473df82468f958445479c59e784896fa24f4a5fc024b0f501
Successfully built termcolor
Installing collected packages: urllib3, pyasn1, idna, charset-normalizer, rsa, requests, pyasn1-modules, oauthlib, cachetools, requests-oauthlib, google-auth, werkzeug, tensorboard-plugin-wit, tensorboard-data-server, protobuf, numpy, markdown, grpcio, google-auth-oauthlib, absl-py, wrapt, tf-estimator-nightly, termcolor, tensorflow-io-gcs-filesystem, tensorboard, opt-einsum, libclang, keras-preprocessing, keras, h5py, google-pasta, gast, flatbuffers, astunparse, tensorflow
Successfully installed absl-py-1.0.0 astunparse-1.6.3 cachetools-5.0.0 charset-normalizer-2.0.12 flatbuffers-2.0 gast-0.5.3 google-auth-2.6.2 google-auth-oauthlib-0.4.6 google-pasta-0.2.0 grpcio-1.44.0 h5py-3.6.0 idna-3.3 keras-2.8.0 keras-preprocessing-1.1.2 libclang-13.0.0 markdown-3.3.6 numpy-1.22.3 oauthlib-3.2.0 opt-einsum-3.3.0 protobuf-3.20.0 pyasn1-0.4.8 pyasn1-modules-0.2.8 requests-2.27.1 requests-oauthlib-1.3.1 rsa-4.8 tensorboard-2.8.0 tensorboard-data-server-0.6.1 tensorboard-plugin-wit-1.8.1 tensorflow-2.8.0 tensorflow-io-gcs-filesystem-0.24.0 termcolor-1.1.0 tf-estimator-nightly-2.8.0.dev2021122109 urllib3-1.26.9 werkzeug-2.1.1 wrapt-1.14.0
Note: you may need to restart the kernel to use updated packages.
In [2]:
pip install pandas

Collecting pandas
  Downloading pandas-1.4.2-cp38-cp38-win_amd64.whl (10.6 MB)
Requirement already satisfied: python-dateutil>=2.8.1 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from pandas) (2.8.2)
Collecting pytz>=2020.1
  Downloading pytz-2022.1-py2.py3-none-any.whl (503 kB)
Requirement already satisfied: numpy>=1.18.5 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from pandas) (1.22.3)
Requirement already satisfied: six>=1.5 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from python-dateutil>=2.8.1->pandas) (1.16.0)
Installing collected packages: pytz, pandas
Successfully installed pandas-1.4.2 pytz-2022.1
Note: you may need to restart the kernel to use updated packages.
In [3]:
pip install pandas_datareader

Note: you may need to restart the kernel to use updated packages.
Collecting pandas_datareader
  Downloading pandas_datareader-0.10.0-py3-none-any.whl (109 kB)
Requirement already satisfied: requests>=2.19.0 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from pandas_datareader) (2.27.1)
Requirement already satisfied: pandas>=0.23 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from pandas_datareader) (1.4.2)
Collecting lxml
  Downloading lxml-4.8.0-cp38-cp38-win_amd64.whl (3.6 MB)
Requirement already satisfied: pytz>=2020.1 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from pandas>=0.23->pandas_datareader) (2022.1)
Requirement already satisfied: numpy>=1.18.5 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from pandas>=0.23->pandas_datareader) (1.22.3)
Requirement already satisfied: python-dateutil>=2.8.1 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from pandas>=0.23->pandas_datareader) (2.8.2)
Requirement already satisfied: six>=1.5 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from python-dateutil>=2.8.1->pandas>=0.23->pandas_datareader) (1.16.0)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from requests>=2.19.0->pandas_datareader) (2021.10.8)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from requests>=2.19.0->pandas_datareader) (1.26.9)
Requirement already satisfied: idna<4,>=2.5 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from requests>=2.19.0->pandas_datareader) (3.3)
Requirement already satisfied: charset-normalizer~=2.0.0 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from requests>=2.19.0->pandas_datareader) (2.0.12)
Installing collected packages: lxml, pandas-datareader
Successfully installed lxml-4.8.0 pandas-datareader-0.10.0
In [4]:
pip install plotly

Collecting plotly
  Downloading plotly-5.6.0-py2.py3-none-any.whl (27.7 MB)
Requirement already satisfied: six in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from plotly) (1.16.0)
Collecting tenacity>=6.2.0
  Downloading tenacity-8.0.1-py3-none-any.whl (24 kB)
Installing collected packages: tenacity, plotly
Successfully installed plotly-5.6.0 tenacity-8.0.1
Note: you may need to restart the kernel to use updated packages.
In [5]:
pip install sklearn

Collecting sklearn
  Downloading sklearn-0.0.tar.gz (1.1 kB)
Collecting scikit-learn
  Downloading scikit_learn-1.0.2-cp38-cp38-win_amd64.whl (7.2 MB)
Collecting threadpoolctl>=2.0.0
  Downloading threadpoolctl-3.1.0-py3-none-any.whl (14 kB)
Collecting joblib>=0.11
  Downloading joblib-1.1.0-py2.py3-none-any.whl (306 kB)
Requirement already satisfied: numpy>=1.14.6 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from scikit-learn->sklearn) (1.22.3)
Collecting scipy>=1.1.0
  Downloading scipy-1.8.0-cp38-cp38-win_amd64.whl (36.9 MB)
Building wheels for collected packages: sklearn
  Building wheel for sklearn (setup.py): started
  Building wheel for sklearn (setup.py): finished with status 'done'
  Created wheel for sklearn: filename=sklearn-0.0-py2.py3-none-any.whl size=1310 sha256=065caeee8f1f6fcb827252fdaa23c4d010c774c78c54f96988e1622db3b6a5c4
  Stored in directory: c:\users\krudko\appdata\local\pip\cache\wheels\22\0b\40\fd3f795caaa1fb4c6cb738bc1f56100be1e57da95849bfc897
Successfully built sklearn
Installing collected packages: threadpoolctl, scipy, joblib, scikit-learn, sklearn
Successfully installed joblib-1.1.0 scikit-learn-1.0.2 scipy-1.8.0 sklearn-0.0 threadpoolctl-3.1.0
Note: you may need to restart the kernel to use updated packages.
In [8]:
import numpy as np
import pandas as pd
import os
import matplotlib.pyplot as plt
import pandas_datareader as web
import datetime as dt
from sklearn.preprocessing import MinMaxScaler
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, LSTM
from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping
import matplotlib.dates as dates
import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots
In [7]:
pip install matplotlib

Collecting matplotlib
  Downloading matplotlib-3.5.1-cp38-cp38-win_amd64.whl (7.2 MB)
Requirement already satisfied: pyparsing>=2.2.1 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from matplotlib) (3.0.4)
Collecting cycler>=0.10
  Downloading cycler-0.11.0-py3-none-any.whl (6.4 kB)
Requirement already satisfied: numpy>=1.17 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from matplotlib) (1.22.3)
Collecting kiwisolver>=1.0.1
  Downloading kiwisolver-1.4.2-cp38-cp38-win_amd64.whl (55 kB)
Collecting pillow>=6.2.0
  Downloading Pillow-9.1.0-cp38-cp38-win_amd64.whl (3.3 MB)
Requirement already satisfied: packaging>=20.0 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from matplotlib) (21.3)
Collecting fonttools>=4.22.0
  Downloading fonttools-4.31.2-py3-none-any.whl (899 kB)
Requirement already satisfied: python-dateutil>=2.7 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from matplotlib) (2.8.2)
Requirement already satisfied: six>=1.5 in c:\users\krudko\.conda\envs\krudkoenv\lib\site-packages (from python-dateutil>=2.7->matplotlib) (1.16.0)
Installing collected packages: pillow, kiwisolver, fonttools, cycler, matplotlib
Successfully installed cycler-0.11.0 fonttools-4.31.2 kiwisolver-1.4.2 matplotlib-3.5.1 pillow-9.1.0
Note: you may need to restart the kernel to use updated packages.
In [9]:
data=pd.read_csv('upload_DJIA_table.csv')
data[0:3]
Out[9]:
Date Open High Low Close Volume Adj Close
0 2016-07-01 17924.240234 18002.380859 17916.910156 17949.369141 82160000 17949.369141
1 2016-06-30 17712.759766 17930.609375 17711.800781 17929.990234 133030000 17929.990234
2 2016-06-29 17456.019531 17704.509766 17456.019531 17694.679688 106380000 17694.679688
In [10]:
data['Date']=pd.to_datetime(data['Date'])
data=data.sort_values('Date')
In [11]:
fig=make_subplots(specs=[[{"secondary_y":False}]])
fig.add_trace(go.Scatter(x=data['Date'],y=data['Open'].rolling(window=7).mean(),name="DJIA"),secondary_y=False,)
fig.update_layout(autosize=False,width=900,height=500,title_text="DJIA")
fig.update_xaxes(title_text="year")
fig.update_yaxes(title_text="prices",secondary_y=False)
fig.show()
In [12]:
n=len(data)
train_data=data[(n//20)*17:(n//20)*19]
test_data=data[(n//20)*19:]
In [13]:
fig=make_subplots(specs=[[{"secondary_y":False}]])
fig.add_trace(go.Scatter(x=train_data['Date'],y=train_data['Open'],name="Train"),secondary_y=False,)
fig.add_trace(go.Scatter(x=test_data['Date'],y=test_data['Open'],name="Test"),secondary_y=False,)
fig.update_layout(autosize=False,width=900,height=500,title_text="DJIA")
fig.update_xaxes(title_text="year")
fig.update_yaxes(title_text="prices",secondary_y=False)
fig.show()
In [14]:
test_data[0:3]
Out[14]:
Date Open High Low Close Volume Adj Close
107 2016-01-29 16090.259766 16466.300781 16090.259766 16466.300781 217940000 16466.300781
106 2016-02-01 16453.630859 16510.980469 16299.469727 16449.179688 114450000 16449.179688
105 2016-02-02 16420.210938 16420.210938 16108.440430 16153.540039 126210000 16153.540039
In [15]:
print(len(train_data))
print(len(test_data))

198
108
In [16]:
scaler = MinMaxScaler(feature_range=(0,1))
scaled_data = scaler.fit_transform(train_data['Open'].values.reshape(-1,1))
In [17]:
prediction_days = 30

x_train = []
y_train = []

for x in range(prediction_days, len(scaled_data)-5):      ######
    x_train.append(scaled_data[x-prediction_days:x, 0])
    y_train.append(scaled_data[x+5, 0])                   ###### predict 5 days after
    
x_train, y_train = np.array(x_train), np.array(y_train)
x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))
In [18]:
print(x_train.shape)
print(y_train.shape)

(163, 30, 1)
(163,)
In [20]:
def LSTM_model():
    
    model = Sequential()    
    model.add(LSTM(units = 50, return_sequences = True, input_shape = (x_train.shape[1],1)))
    model.add(Dropout(0.2))
    model.add(LSTM(units = 50, return_sequences = True))
    model.add(Dropout(0.2))
    model.add(LSTM(units = 50))
    model.add(Dropout(0.2))
    model.add(Dense(units=1))
    
    return model
In [21]:
model = LSTM_model()
model.summary()
model.compile(optimizer='adam', loss='mean_squared_error', metrics = ['accuracy'])

Model: "sequential"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 lstm (LSTM)                 (None, 30, 50)            10400     
                                                                 
 dropout (Dropout)           (None, 30, 50)            0         
                                                                 
 lstm_1 (LSTM)               (None, 30, 50)            20200     
                                                                 
 dropout_1 (Dropout)         (None, 30, 50)            0         
                                                                 
 lstm_2 (LSTM)               (None, 50)                20200     
                                                                 
 dropout_2 (Dropout)         (None, 50)                0         
                                                                 
 dense (Dense)               (None, 1)                 51        
                                                                 
=================================================================
Total params: 50,851
Trainable params: 50,851
Non-trainable params: 0
_________________________________________________________________
In [22]:
checkpointer = ModelCheckpoint(filepath = 'weights_best.hdf5', verbose = 1, save_best_only = True)
his=model.fit(x_train,y_train,epochs=20,batch_size=32,callbacks=[checkpointer])

Epoch 1/20
5/6 [========================>.....] - ETA: 0s - loss: 0.1939 - accuracy: 0.0063WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 7s 54ms/step - loss: 0.1927 - accuracy: 0.0061
Epoch 2/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0746 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 56ms/step - loss: 0.0740 - accuracy: 0.0000e+00
Epoch 3/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0667 - accuracy: 0.0063WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 70ms/step - loss: 0.0665 - accuracy: 0.0061
Epoch 4/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0584 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 58ms/step - loss: 0.0575 - accuracy: 0.0000e+00
Epoch 5/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0591 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 57ms/step - loss: 0.0591 - accuracy: 0.0000e+00
Epoch 6/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0528 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 63ms/step - loss: 0.0522 - accuracy: 0.0000e+00
Epoch 7/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0485 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 59ms/step - loss: 0.0504 - accuracy: 0.0000e+00
Epoch 8/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0498 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 55ms/step - loss: 0.0502 - accuracy: 0.0000e+00
Epoch 9/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0528 - accuracy: 0.0063    WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 56ms/step - loss: 0.0526 - accuracy: 0.0061
Epoch 10/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0475 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 56ms/step - loss: 0.0474 - accuracy: 0.0000e+00
Epoch 11/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0507 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 57ms/step - loss: 0.0503 - accuracy: 0.0000e+00
Epoch 12/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0478 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 62ms/step - loss: 0.0503 - accuracy: 0.0000e+00
Epoch 13/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0499 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 59ms/step - loss: 0.0496 - accuracy: 0.0000e+00
Epoch 14/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0456 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 58ms/step - loss: 0.0462 - accuracy: 0.0000e+00
Epoch 15/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0443 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 87ms/step - loss: 0.0444 - accuracy: 0.0000e+00
Epoch 16/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0472 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 56ms/step - loss: 0.0466 - accuracy: 0.0000e+00
Epoch 17/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0411 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 58ms/step - loss: 0.0406 - accuracy: 0.0000e+00
Epoch 18/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0413 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 81ms/step - loss: 0.0413 - accuracy: 0.0000e+00
Epoch 19/20
5/6 [========================>.....] - ETA: 0s - loss: 0.0414 - accuracy: 0.0000e+00WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 59ms/step - loss: 0.0423 - accuracy: 0.0000e+00
Epoch 20/20
6/6 [==============================] - ETA: 0s - loss: 0.0483 - accuracy: 0.0061WARNING:tensorflow:Can save best model only with val_loss available, skipping.
6/6 [==============================] - 0s 76ms/step - loss: 0.0483 - accuracy: 0.0061
In [23]:
plt.plot(his.history['loss'])
plt.plot(his.history['accuracy'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['loss','accuracy'], loc='upper right')
plt.show()
In [24]:
actual_prices = test_data['Open'].values
total_dataset = pd.concat((train_data['Open'], test_data['Open']), axis=0)

model_inputs = total_dataset[len(total_dataset)-len(test_data)-prediction_days:].values
model_inputs = model_inputs.reshape(-1,1)
model_inputs = scaler.transform(model_inputs)
In [25]:
x_test = []
for x in range(prediction_days,len(model_inputs)):
    x_test.append(model_inputs[x-prediction_days:x,0])

x_test = np.array(x_test)
x_test = np.reshape(x_test,(x_test.shape[0],x_test.shape[1],1))

predicted_prices = model.predict(x_test)
predicted_prices = scaler.inverse_transform(predicted_prices)
In [33]:
plt.plot(actual_prices, color='magenta', label=f"Actual price")
plt.plot(predicted_prices, color= 'green', label=f"Predicted 5-days-after price")
plt.title(f"DJIA Stock")
plt.xlabel("Days in test period")
plt.ylabel(f"Price")
plt.legend()
plt.show()
In [27]:
test_data['predict']=predicted_prices
test_data[0:10]

C:\Users\krudko\AppData\Local\Temp\ipykernel_11344\2743983796.py:1: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
Out[27]:
Date Open High Low Close Volume Adj Close predict
107 2016-01-29 16090.259766 16466.300781 16090.259766 16466.300781 217940000 16466.300781 16289.003906
106 2016-02-01 16453.630859 16510.980469 16299.469727 16449.179688 114450000 16449.179688 16266.957031
105 2016-02-02 16420.210938 16420.210938 16108.440430 16153.540039 126210000 16153.540039 16263.038086
104 2016-02-03 16186.200195 16381.690430 15960.450195 16336.660156 141870000 16336.660156 16276.891602
103 2016-02-04 16329.669922 16485.839844 16266.160156 16416.580078 131490000 16416.580078 16300.595703
102 2016-02-05 16417.949219 16423.630859 16129.809570 16204.969727 139010000 16204.969727 16331.568359
101 2016-02-08 16147.509766 16147.509766 15803.549805 16027.049805 165880000 16027.049805 16369.849609
100 2016-02-09 16005.410156 16136.620117 15881.110352 16014.379883 127740000 16014.379883 16408.748047
99 2016-02-10 16035.610352 16201.889648 15899.910156 15914.740234 122290000 15914.740234 16441.806641
98 2016-02-11 15897.820312 15897.820312 15503.009766 15660.179688 172070000 15660.179688 16466.044922
In [28]:
fig=make_subplots(specs=[[{"secondary_y":False}]])
fig.add_trace(go.Scatter(x=train_data['Date'],y=train_data['Open'],name="Train Actual"),secondary_y=False,)
fig.add_trace(go.Scatter(x=test_data['Date'],y=test_data['Open'],name="Test Actual"),secondary_y=False,)
fig.add_trace(go.Scatter(x=test_data['Date'],y=test_data['predict'],name="Predicted 5-days after price"),secondary_y=False,)
fig.update_layout(autosize=False,width=900,height=500,title_text="DJIA")
fig.update_xaxes(title_text="year")
fig.update_yaxes(title_text="prices",secondary_y=False)
fig.show()
In [29]:
real_data = [model_inputs[len(model_inputs)+1-prediction_days:len(model_inputs+1),0]]
real_data = np.array(real_data)
real_data = np.reshape(real_data,(real_data.shape[0],real_data.shape[1],1))
print(real_data.shape)

(1, 29, 1)
In [ ]:
In [ ]: